Welcome to the Cyber Threat Prediction project repository! This project aims to develop and deploy advanced predictive models for cyber threat detection, providing valuable insights and real-time updates on potential cyber attacks.
In this project, we have developed two primary predictive models:
-
Model 1: Utilizing neural networks, this model predicts future cyber threats with over three years of accuracy. It has been trained on a comprehensive dataset spanning the last 10 years, enabling robust forecasting capabilities.
-
Model 2: Employing the Random Forest algorithm, this model detects ongoing cyber attacks in real-time by analyzing network traffic data from any company. It efficiently distinguishes between normal traffic and suspicious activities, enhancing proactive threat detection.
- User-friendly Website: A web interface has been developed to facilitate easy uploading of company datasets for threat prediction.
- Real-time Updates: APIs have been implemented to provide real-time updates on global cyber attacks, ensuring timely awareness of emerging threats.
- Interactive Dashboards: Embedded Tableau dashboards visualize past cyber attacks on nations, including detailed descriptions and mitigation strategies. Additionally, they offer comparative analysis through Cyber Exposure Index (CEI), Cyber Governance Index (CGI), National Cyber Security Index (NCSI), and Digital Dependency Index (DDL) for each nation.
- Efficient Data Management: MongoDB is utilized for storing and managing the data collected and generated by the predictive models.
- HTML, CSS, JavaScript: For the development of the user interface.
- Python: For building and training the predictive models.
- MongoDB: For efficient storage and management of data.
- Tableau: For creating interactive dashboards.
- Flask: For developing the web application.
To get started with the project, follow these steps:
- Clone the repository to your local machine.
- Install the necessary dependencies listed in
requirements.txt. - Run the web application using Flask.
- Images have been attached for reference.
Contributions to the project are welcome! Feel free to open issues for any bugs or feature requests, and submit pull requests with your enhancements.